Local Context-Aware Active Domain Adaptation

TL;DR

This paper introduces LADA, a local context-aware active domain adaptation framework that selects informative target samples based on local prediction inconsistency, improving adaptation performance with limited labels.

Contribution

The paper proposes a novel local inconsistency-based criterion for sample selection and a class-balanced augmentation strategy for efficient domain adaptation.

Findings

LADA outperforms existing ADA methods on various benchmarks.

The local inconsistency criterion selects more informative samples.

Augmentation with confident neighbors improves adaptation efficiency.

Abstract

Active Domain Adaptation (ADA) queries the labels of a small number of selected target samples to help adapting a model from a source domain to a target domain. The local context of queried data is important, especially when the domain gap is large. However, this has not been fully explored by existing ADA works. In this paper, we propose a Local context-aware ADA framework, named LADA, to address this issue. To select informative target samples, we devise a novel criterion based on the local inconsistency of model predictions. Since the labeling budget is usually small, fine-tuning model on only queried data can be inefficient. We progressively augment labeled target data with the confident neighbors in a class-balanced manner. Experiments validate that the proposed criterion chooses more informative target samples than existing active selection strategies. Furthermore, our full method clearly surpasses recent ADA arts on various benchmarks. Code is available at https://github.com/tsun/LADA.